Chung-Sheng Li

Transcoding Internet content for heterogeneous client devices

There is a growing diversity of client devices that have access to the Internet. However, much of the content on the Internet cannot be handled by the devices that have limited communication, processing, storage and display capabilities. In order to improve the utility of a wide range of client devices, we propose a network-based solution for transcoding Internet content. The system uses an InfoPyramid for representing and transcoding video, images, audio and text. The InfoPyramid manipulates the content along the dimensions of fidelity and modality, and aggregates the methods for content analysis, translation, filtering and selection. The InfoPyramid utilizes a policy engine, which incorporates user and publisher preferences, various transcoding policies, device descriptions, and real-time network constraints in order to adapt the Internet content to the client devices.

Content-based transcoding of images in the Internet

We present a system for transcoding images in the Internet in order to improve their delivery to client devices with a wide range of communication, processing, storage and display capabilities. The content-based image transcoder analyzes the images in order to classify them into image type and image purpose classes. The system then utilizes transcoding policies based on the content classes to manipulate and transcode the images. We describe the image transcoding process for a variety of client devices, including PDAs, hand-held computers (HHCs), TV browsers and color PCs, and demonstrate improvements in delivery speed and accessibility of the images in the Internet.

Multimedia content description in the InfoPyramid

There is a growing need for developing a content description language for multimedia that improves searching, indexing and managing of the multimedia content. The MPEG group established the MPEG-7 effort to standardize the multimedia content interface. The proposed interface will bridge the gap between various types of content meta-data, such as content features, annotations, relationships, and the search engines. We develop a method of handling multimedia content description in a new multi-abstraction, multi-modal content representation framework called the InfoPyramid. The InfoPyramid facilitates the search, retrieval, manipulation, and transmission of multimedia data by providing a hierarchy for content descriptors. We illustrate the suitability of the InfoPyramid multimedia content description to MPEG-7 by examining four multimedia retrieval applications: a Web-image search engine, a satellite image retrieval system, an Internet content delivery system, and a TV news storage and retrieval system.

Progressive search and retrieval in large image archives

In this paper, we describe the architecture and implementation of a framework to perform content-based search of an image database, where content is specified by the user at one or more of the following three abstraction levels: pixel, feature, and semantic. This framework incorporates a methodology that yields a computationally efficient implementation of image-processing algorithms, thus allowing the efficient extraction and manipulation of user-specified features and content during the execution of queries. The framework is well suited for searching scientific databases, such as satellite-image-, medical-, and seismic-data repositories, where the volume and diversity of the information do not allow the a priori generation of exhaustive indexes, but we have successfully demonstrated its usefulness on still-image archives.

Clustering and singular value decomposition for approximate indexing in high dimensional spaces

High-dimensionality indexing of feature spaces is critical for many data-intensive applications such as content-based retrieval of images or video from multimedia databases and similarity retrieval of patterns in data mining. Unfortunately, the performance of nearest neighbor (NN) queries, which are required for similarity search, deteriorates rapidly with the increase in the number of dimensions. We propose the Clustering with Singular Value Decomposition (CSVD) method, which combines clustering and singular value decomposition (SVD) to reduce the number of index dimensions, while maintaining a reasonably high precision for a given value of recall. In the proposed CSVD method, homogeneous points are grouped into clusters such that the points in each cluster are more amenable to dimensionality reduction than the original dataset. Experiments with texture vectors extracted from satellite images show that CSVD achieves signi cantly higher dimensionality reduction than SVD for the same fraction of total variance preserved. Conversely, for the same compression ratio CSVD results in an increase in preserved total variance with respect to SVD (e.g., a 70% increase for a 20:1 compression ratio). This translates to a higher e ciency in processing approximate NN queries, as quanti ed through experimental results.

Deriving texture feature set for content-based retrieval of satellite image database

In this paper, the performance of similarity retrieval from satellite image databases by using different sets of spatial and transformed-based texture features is evaluated and compared. A benchmark consisting of 37 satellite image clips from various satellite instruments is devised for the experiments. We show that although the proposed feature set perform only slightly better with the Brodatz set, its performance is far superior for the satellite images. The result indicates that more than 25% of the benchmark patterns can be retrieved with more than 80% accuracy by using normalized Euclidean distance. In contrast, less than 10% of the patterns are retrieved with more than 80% accuracy by using transformed-based feature sets (such as those based on Gabor filter or quadrature mirror filter (QMF)).

Dynamic assembly of views in data cubes

In this paper, we present a method for dynamically assembling views in multi-dimensional data cubes in order to more e ciently support data analysis and querying involving aggregations. The proposed method decomposes the data cubes into an indexed hierarchy of view elements. The view elements di er from traditional data cube cells in that they correspond to partial and residual aggregations of the data cube. The view elements provide highly granular building blocks for synthesizing the aggregated and rangeaggregated views of the data cubes. We propose a strategy for selecting and materializing the view elements based on the frequency of view access. This allows the dynamic adaptation of the view element sets to patterns of retrieval. We present a fast and optimal algorithm for selecting non-expansive view element sets that minimize the processing costs for generating a population of aggregated views. We also present a greedy algorithm for selecting redundant view element sets in order to further reduce processing costs. We demonstrate that the view element approaches perform better in terms of lower processing and storage costs than methods based on materializing views.

Sequential processing for content-based retrieval of composite objects

It is becoming increasingly important for multimedia databases to provide capabilities for content-based retrieval of composite objects. Composite objects consist of several simple objects which have feature, spatial, temporal, semantic attributes, and spatial and temporal relationships between them. A content-based composite object query is satisfied by evaluating a program of content-based rules (i.e., color, texture), spatial and temporal rules (i.e., east, west), fuzzy conjunctions (i.e., appears similar AND is spatially near) and database lookups (i.e., semantics). We propose a new sequential processing method for efficiently computing content-based queries of composite objects. The proposed method evaluates the composite object queries by (1) defining an efficient ordering of the sub-goals of the query, which involve spatial, temporal, content-based and fuzzy rules, (2) developing a query block management strategy for generating, evaluating, and caching intermediate sub-goal results, and (3) conducting a best-first dynamic programming-based search with intelligent back-tracking. The method is guaranteed to find the optimal answer to the query and reduces the query time by avoiding the exploration of unlikely candidates.

Progressive classification in the compressed domain for large EOS satellite databases

We introduce a new framework for classifying large images (in the EOS; Earth Observing System) that is more accurate and less computationally expensive than the classical pixel-by-pixel approach. This approach, called progressive classification, is well suited for analyzing large images, such as multispectral satellite scenes, compressed with wavelet-based or block-transform-based transformations. These transformations produce a multiresolution pyramid representation of the data. A progressive classifier analyses the image at the coarsest resolution level, and it decides whether each coefficient corresponds to a homogeneous block of pixels in the original image or to a heterogeneous block. In the first case it labels the block, in the second case it recursively analyzes the region of the image at the immediately finer resolution level. Computational efficiency, compared to the classical approach, results from examining a much smaller number of coefficients than the number of pixels in the original image. Thus, progressive classification is a prime candidate as a content-based search operator for remotely-sensed data.

Adaptive storage and retrieval of large compressed images

Enabling the efficient storage, access and retrieval of large volumes of multidimensional data is one of the important emerging problems in databases. We present a framework for adaptively storing, accessing, and retrieving large images. The framework uses a space and frequency graph to generate and select image view elements for storing in the database. By adapting to user access patterns, the system selects and stores those view elements that yield the lowest average cost for accessing the multiresolution subregion image views. The system uses a second adaptation strategy to divide computation between server and client in progressive retrieval of image views using view elements. We show that the system speeds-up retrieval for access and retrieval modes, such as drill-down browsing and remote zooming and panning, and minimizes the amount of data transfer over the network.